Skip to content

Multi-tier framework for evaluating AI agent skills and plugins with quality gates, security scanning, harness compatibility checks, semantic overlap detection, synthetic evaluation dataset generation, and live agent evaluation that measures how skills affect agent behavior. Ships reusable CI templates that bring every check to any repository.

5.2 KB
Raw Blame
# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0

instances:
  - url: nvidia-skillevaluator.docs.buildwithfern.com/skills/skillevaluator
    custom-domain: docs.nvidia.com/skills/skillevaluator
    multi-source: true

title: SkillEvaluator Documentation

global-theme: nvidia

navbar-links:
  - type: github
    value: https://github.com/NVIDIA/SkillEvaluator

logo:
  light: ../docs/assets/skillevaluator-logo.svg
  dark: ../docs/assets/skillevaluator-logo.svg
  height: 28
  right-text: SkillEvaluator

favicon: ../docs/assets/skillevaluator-logo.svg

navigation:
  - page: Overview
    path: ../docs/index.mdx
    slug: /
  - section: Get Started
    skip-slug: true
    contents:
      - page: Installation
        path: ../docs/installation.mdx
        slug: installation
      - page: Quickstart
        path: ../docs/quickstart.mdx
        slug: quickstart
      - page: Repository Integration
        path: ../docs/repository-integration.mdx
        slug: repository-integration
      - page: Evaluate from Your Agent
        path: ../docs/agent-skill.mdx
        slug: agent-skill
  - section: Set Up
    skip-slug: true
    contents:
      - page: Providers & Credentials
        path: ../docs/configuration.mdx
        slug: configuration
      - page: Agents & Sandboxes
        path: ../docs/agents-and-sandboxes.mdx
        slug: agents-and-sandboxes
  - section: Evaluate Your Skill
    skip-slug: true
    contents:
      - page: "Tier 1: Validation"
        path: ../docs/tier1-validation.mdx
        slug: tier1-validation
      - page: "Tier 1: Harness Check"
        path: ../docs/harness-check.mdx
        slug: harness-check
      - page: "Tier 2: Deduplication"
        path: ../docs/tier2-deduplication.mdx
        slug: tier2-deduplication
      - page: "Tier 3: Live Agent Evaluation"
        path: ../docs/tier3-live-evaluation.mdx
        slug: tier3-live-evaluation
      - page: Prepare a Dataset
        path: ../docs/prepare-dataset.mdx
        slug: prepare-dataset
      - page: Configure a Tier 3 Run
        path: ../docs/tier3-run-options.mdx
        slug: tier3-run-options
      - page: NeMo Gym Integration
        path: ../docs/nemo-gym.mdx
        slug: nemo-gym
      - page: Grader Validation
        path: ../docs/grader-validation.mdx
        slug: grader-validation
      - page: Trace Datasets
        path: ../docs/trace-datasets.mdx
        slug: trace-datasets
      - page: Custom Graders & Tasks
        path: ../docs/custom-graders.mdx
        slug: custom-graders
      - page: Reproducible Terminal Demo
        path: ../docs/starter-demo.mdx
        slug: starter-demo
  - section: Results & CI
    skip-slug: true
    contents:
      - page: Reports & Results
        path: ../docs/reports.mdx
        slug: reports
      - page: Metrics Reference
        path: ../docs/metrics-reference.mdx
        slug: metrics-reference
      - page: Performance Dashboard
        path: ../docs/performance-dashboard.mdx
        slug: performance-dashboard
      - page: "BENCHMARK.md Rollout and Backfill"
        path: ../docs/benchmark-rollout.mdx
        slug: benchmark-rollout
      - page: GitHub Actions
        path: ../docs/github-actions.mdx
        slug: github-actions
      - page: GitHub CLI Setup
        path: ../docs/cli-onboarding.mdx
        slug: cli-onboarding
      - page: GitLab CI/CD
        path: ../docs/gitlab-ci.mdx
        slug: gitlab-ci
      - page: Gate Your CI
        path: ../docs/ci-integration.mdx
        slug: ci-integration
  - section: Reference
    skip-slug: true
    contents:
      - page: Installation Options
        path: ../docs/installation-options.mdx
        slug: installation-options
      - page: Tier 1 Checks and Policies
        path: ../docs/tier1-reference.mdx
        slug: tier1-reference
      - page: Tier 2 Checks and Limits
        path: ../docs/tier2-reference.mdx
        slug: tier2-reference
      - section: Live Evaluation
        skip-slug: true
        contents:
          - page: Run Options and Cost
            path: ../docs/tier3-run-reference.mdx
            slug: tier3-run-reference
          - page: Dataset Format and Policy
            path: ../docs/eval-datasets.mdx
            slug: eval-datasets
          - page: Interpret Results
            path: ../docs/tier3-results.mdx
            slug: tier3-results
          - page: Grading and Evidence
            path: ../docs/tier3-grading.mdx
            slug: tier3-grading
          - page: Runtime and Backends
            path: ../docs/tier3-runtime.mdx
            slug: tier3-runtime
          - page: Interaction and Activation
            path: ../docs/tier3-experiments.mdx
            slug: tier3-experiments
      - page: CLI Reference
        path: ../docs/cli-reference.mdx
        slug: cli-reference
      - page: Environment Variables
        path: ../docs/environment-variables.mdx
        slug: environment-variables
      - page: Advanced CI
        path: ../docs/advanced-ci.mdx
        slug: advanced-ci
      - page: Contributing
        path: ../docs/developer-guide.mdx
        slug: developer-guide
      - link: NVIDIA Verified Skills
        href: https://docs.nvidia.com/skills/